© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10475
    Prev
    Next
    INDEX
    Explanations

    array indexing and pointer arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite

    list operations and array indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    append
    0.40
     Marke
    0.39
     coda
    0.39
    (/
    0.37
     ah
    0.37
     get
    0.37
     zak
    0.37
     prep
    0.36
    ords
    0.36
     price
    0.36
    POSITIVE LOGITS
    '][$
    0.69
    [$
    0.56
    [(\
    0.55
    [++
    0.55
    [(
    0.54
    [_
    0.54
     objectAtIndex
    0.49
    []');
    0.49
    这款
    0.47
    elementAt
    0.47
    Activations Density 0.001%

    No Known Activations